检索结果-内蒙古大学图书馆

Reliable and Balanced Transfer Learning for Generalized Multimodal Face Anti-Spoofing

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Lin, Xun Liu, Ajian Yu, Zitong Cai, Rizhao Wang, Shuai Yu, Yi Wan, Jun Lei, Zhen Cao, Xiaochun Kot, Alex Beihang University School of Computer Science and Engineering Beijing China Beijing China Great Bay University Dongguan China Lab Singapore Macau University of Science and Technology Taipa China School of Artificial Intelligence Beijing China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Hong Kong Shenzhen Campus of Sun Yat-sen University Shenzhen China

Face Anti-Spoofing (FAS) is essential for securing face recognition systems against presentation attacks. Recent advances in sensor technology and multimodal learning have enabled the development of multimodal FAS systems. However, existing methods often struggle to generalize to unseen attacks and diverse environments due to two key challenges: (1) Modality unreliability, where sensors such as depth and infrared suffer from severe domain shifts, impairing the reliability of cross-modal fusion;and (2) Modality imbalance, where over-reliance on a dominant modality weakens the model's robustness against attacks that affect other modalities. To overcome these issues, we propose MMDG++, a multimodal domain-generalized FAS framework built upon the vision-language model CLIP. In MMDG++, we design the Uncertainty-Guided Cross-Adapter++ (U-Adapter++) to filter out unreliable regions within each modality, enabling more reliable multimodal interactions. Additionally, we introduce Rebalanced Modality Gradient Modulation (ReGrad) for adaptive gradient modulation to balance modality convergence. To further enhance generalization, propose Asymmetric Domain Prompts (ADPs) that leverage CLIP's language priors to learn generalized decision boundaries across modalities. We also develop a novel multimodal FAS benchmark to evaluate generalizability under various deployment conditions. Extensive experiments across this benchmark show our method outperforms state-of-the-art FAS methods, demonstrating superior generalization capability. © 1979-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration 16th

PIPAL: A Large-Scale Image Quality Assessment Dataset for Pe...

引用

16th European Conference on computer Vision, ECCV 2020

作者： Jinjin, Gu Haoming, Cai Haoyu, Chen Xiaoxing, Ye Ren, Jimmy S. Chao, Dong The School of Data Science The Chinese University of Hong Kong Shenzhen China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China SenseTime Research Science Park Hong Kong SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9783030586201

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based methods, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Robust Self-Expression Learning with Adaptive Noise Perception

SSRN

引用

SSRN 2023年

作者： Wang, Yangbo Zhou, Jie Lu, Jianglin Wan, Jun Gao, Can Lin, Qingshui College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China SMILE Lab Department of ECE College of Engineering Northeastern University Boston02115 United States School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan430073 China Basic Teaching Department Liaoning Technical University Huludao125105 China

Self-expression learning methods often obtain a coefficient matrix to measure the similarity between pairs of samples. However, directly using the raw data to represent each sample under the self-expression framework may not be ideal, as noise points are inevitably involved in the process of representing clean samples. To address this issue, this work proposes a novel self-expression model called robust Self-Expression learning with adaptive Noise Perception (SENP). SENP decomposes each sample into a clean part and a noisy part, and samples with large self-expression losses can be recognized as the noise points. A reliable coefficient matrix can then be learned by using only the clean points to reconstruct the clean part of each sample. By simultaneously detecting the noisy part of each sample and noise points, and adaptively mitigating their negative impacts, the representative ability of the generated coefficient matrix is improved. Moreover, inspired by the solution of non-negative matrix factorization (NMF), an effective algorithm is formed to optimize SENP. Extensive experiments on well-known benchmark datasets demonstrate the superiority of SENP compared to several state-of-the-art methods. © 2023, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Dojo: A Differentiable Physics Engine for robotics

arXiv

引用

arXiv 2022年

作者： Howell, Taylor A. Le Cleac'h, Simon Brüdigam, Jan Kolter, J. Zico Schwager, Mac Manchester, Zachary The Department of Mechanical Engineering Stanford University StanfordCA94305 United States The School of Computation Information and Technology Technical University of Munich Munich80333 Germany The Department of Computer Science Carnegie Mellon University PittsburghPA15213 United States The Department of Aeronautics and Astronautics Stanford University StanfordCA94305 United States The Robotics Institute Carnegie Mellon University PittsburghPA15213 United States

We present Dojo, a differentiable physics engine for robotics that prioritizes stable simulation, accurate contact physics, and differentiability with respect to states, actions, and system parameters. Dojo achieves stable simulation at low sample rates and conserves energy and momentum by employing a variational integrator. A nonlinear complementarity problem with second-order cones for friction models hard contact, and is reliably solved using a custom primal-dual interior-point method. Special properties of the interior-point method are exploited using implicit differentiation to efficiently compute smooth gradients that provide useful information through contact events. We demonstrate Dojo with a number of examples including: planning, policy optimization, and system identification, that demonstrate the engine's unique ability to simulate hard contact while providing smooth, analytic gradients. Copyright © 2022, The Authors. All rights reserved.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction

arXiv

引用

arXiv 2022年

作者： Zhao, Ruiyang He, Zhao Wang, Tao Qiu, Suhao Herman, Pawel Hu, Yanle Zhang, Chencheng Shen, Dinggang Sun, Bomin Yang, Guang-Zhong Feng, Yuan School of Biomedical Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL United States Department of Neurosurgery Center for Functional Neurosurgery Ruijin Hospital Shanghai Jiao Tong University School of Medicine Shanghai China Division of computational science and technology KTH Royal Institute of Technology Stockholm Sweden Department of Radiation Oncology Mayo Clinic in Arizona PhoenixAZ United States School of Biomedical Engineering ShanghaiTech University Shanghai201210 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

Interventional magnetic resonance imaging (i-MRI) for surgical guidance could help visualize the interventional process such as deep brain stimulation (DBS), improving the surgery performance and patient outcome. Different from retrospective reconstruction in conventional dynamic imaging, i-MRI for DBS has to acquire and reconstruct the interventional images sequentially online. Here we proposed a convolutional long short-term memory (Conv-LSTM) based recurrent neural network (RNN), or ConvLR, to reconstruct interventional images with golden-angle radial sampling. By using an initializer and Conv-LSTM blocks, the priors from the preoperative reference image and intra-operative frames were exploited for reconstructing the current frame. Data consistency for radial sampling was implemented by a soft-projection method. To improve the reconstruction accuracy, an adversarial learning strategy was adopted. A set of interventional images based on the pre-operative and postoperative MR images were simulated for algorithm validation. Results showed with only 10 radial spokes, ConvLR provided the best performance compared with state-of-the-art methods, giving an acceleration up to 40 folds. The proposed algorithm has the potential to achieve real-time i-MRI for DBS and can be used for general purpose MR-guided intervention. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Accurate, interpretable, and fast animation: An iterative, sparse, and nonconvex approach

arXiv

引用

arXiv 2021年

作者： Racković, Stevo Soares, Cláudia Jakovetić, Dušan Desnica, Zoranka Institute for Systems and Robotics Instituto Superior Técnico Lisbon1049-001 Portugal Computer Science Department NOVA School of Science and Technology Caparica2825-149 Portugal Department of Mathematics Faculty of Sciences University of Novi Sad Novi Sad21000 Serbia 3Lateral Animation Studio Epic Games Company

Digital human animation relies on high-quality 3D models of the human face-rigs. A face rig must be accurate and, at the same time, fast to compute. One of the most common rigging models is the blendshape model. We propose a novel algorithm for solving the nonconvex inverse rig problem in facial animation. Our approach is model-based, but in contrast with previous model-based approaches, we use a quadratic instead of the linear approximation to the higher order rig model. This increases the accuracy of the solution by 8% (0:26mm) on average and, confirmed by the empirical results, increases the sparsity of the resulting parameter vector-an important feature for interpretability by animation artists. The proposed solution is based on a Levenberg-Marquardt (LM) algorithm, applied to a nonconvex constrained problem with sparsity regularization. In order to reduce the complexity of the iterates, a paradigm of Majorization Minimization (MM) is further invoked, which leads to an easy to solve problem that is separable in the parameters at each algorithm iteration. The algorithm is evaluated on a number of animation datasets, proprietary and open-source, and the results indicate the superiority of our method compared to the standard approach based on the linear rig approximation. Although our algorithm targets the specific problem, it might have additional signal processing applications. © 2021, CC BY-NC-SA.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Modeling and Detecting Communities in Node Attributed Networks

arXiv

引用

arXiv 2021年

作者： Ren, Ren Shao, Jinliang Bishop, Adrian N. Zheng, Wei Xing School of Automation Engineering University of Electronic Science and Technology of China 611731 China The Research Center on Crowd Spectrum Intelligence Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518054 China Australia Canberra Research Lab Australia The School of Computer Data and Mathematical Sciences Western Sydney University SydneyNSW2751 Australia

As a fundamental structure in real-world networks, in addition to graph topology, communities can also be reflected by abundant node attributes. In attributed community detection, probabilistic generative models (PGMs) have become the mainstream method due to their principled characterization and competitive performances. Here, we propose a novel PGM without imposing any distributional assumptions on attributes, which is superior to the existing PGMs that require attributes to be categorical or Gaussian distributed. Based on the block model of graph structure, our model incorporates the attribute by describing its effect on node popularity. To characterize the effect quantitatively, we analyze the community detectability for our model and then establish the requirements of the node popularity term. This leads to a new scheme for the crucial model selection problem in choosing and solving attributed community detection models. With the model determined, an efficient algorithm is developed to estimate the parameters and to infer the communities. The proposed method is validated from two aspects. First, the effectiveness of our algorithm is theoretically guaranteed by the detectability condition. Second, extensive experiments indicate that our method not only outperforms the competing approaches on the employed datasets, but also shows better applicability to networks with various node attributes. © 2021, CC BY.

关键词： Population dynamics

来源：评论

学校读者我要写书评

暂无评论

An infinite class of Neumaier graphs and non-existence results

arXiv

引用

arXiv 2021年

作者： Abiad, Aida Castryck, Wouter de Boeck, Maarten Koolen, Jack H. Zeijlemaker, Sjanne Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Department of Mathematics: Analysis Logic and Discrete Mathematics Ghent University Flanders Belgium Department of Mathematics and Data Science Vrije Universiteit Brussel Belgium Imec-COSIC Department of Electrical Engineering KU Leuven Belgium Department of Mathematics: Algebra and Geometry Ghent University Flanders Belgium School of Mathematical Sciences University of Science and Technology of China Hefei China CAS Wu Wen-Tsun Key Laboratory of Mathematics University of Science and Technology of China Hefei China

A Neumaier graph is a non-complete edge-regular graph containing a regular clique. A Neumaier graph that is not strongly regular is called a strictly Neumaier graph. In this work we present a new construction of strictly Neumaier graphs, and using Jacobi sums, we show that our construction produces infinitely many instances. Moreover, we prove some necessary conditions for the existence of (strictly) Neumaier graphs that allow us to show that several parameter sets are not admissible. Copyright © 2021, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-of-use pricing for energy storage investment

arXiv

引用

arXiv 2021年

作者： Zhao, Dongwei Wang, Hao Huang, Jianwei Lin, Xiaojun MIT Energy Initiative Massachusetts Institute of Technology CambridgeMA02139 United States Department of Data Science and Artificial Intelligence Faculty of Information Technology Monash University MelbourneVIC3800 Australia School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States

Time-of-use (ToU) pricing is widely used by the electricity utility to shave peak load. Such a pricing scheme provides users with incentives to invest in behind-the-meter energy storage and to shift peak load towards low-price intervals. However, without considering the implication on energy storage investment, an improperly designed ToU pricing scheme may lead to significant welfare loss, especially when users over-invest the storage, which leads to new energy consumption peaks. In this paper, we will study how to design a social-optimum ToU pricing scheme by explicitly considering its impact on storage investment. We model the interactions between the utility and users as a two-stage optimization problem. To resolve the challenge of asymmetric information due to users’ private storage cost, we propose a ToU pricing scheme based on different storage types and the aggregate demand per type. Each user does not need to reveal his private cost information. We can further compute the optimal ToU pricing with only a linear complexity. Simulations based on real-world data show that the suboptimality gap of our proposed ToU pricing, compared with the social optimum achieved under complete information, is less than 5%. © 2021, CC BY.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

HITTSFL: Design of a Cost-Effective HIS-Insensitive TNU-Tolerant and SET-Filterable Latch for Safety-Critical Applications

HITTSFL: Design of a Cost-Effective HIS-Insensitive TNU-Tole...

引用

Design Automation Conference

作者： Aibin Yan Xiangfeng Feng Xiaohu Zhao Hang Zhou Jie Cui Zuobin Ying Patrick Girard Xiaoqing Wen Anhui Engineering Laboratory of IoT Security Technologies / School of Computer Science and Technology Anhui University Hefei China Laboratory of Informatics Robotics and Microelectronics of Montpellier University of Montpellier / CNRS Montpellier France Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan

ISBN: (数字)9781728110851

ISBN: (纸本)9781728158020

This paper proposes a cost-effective, high-impedance-state (HIS)-insensitive, triple-node-upset (TNU)-tolerant and single-event-transient (SET)-filterable latch, namely HITTSFL, to ensure high reliability with low-cost. The latch mainly comprises an output-level SET-filterable Schmitt-trigger and three inverters that make the values stored in three parallel single-node-upset (SNU)-recoverable dual-interlocked-storage-cells (DICEs) converge at a common node to tolerate any possible TNU. The latch does not use C-elements to be insensitive to the HIS. Simulation results demonstrate the TNU-tolerability and SET-filterability of the proposed HITTSFL latch. Moreover, due to the use of clock-gating technologies and fewer transistors, the proposed latch can reduce delay, power, and area by 76.65%, 6.16%, and 28.55%, respectively, compared with the state-of-the-art TNU hardened latch (TNUHL) that cannot filter SETs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：